Adam

Value Members

1. final def !=(arg0: AnyRef): Boolean

   Definition Classes

   AnyRef

2. final def !=(arg0: Any): Boolean

   Definition Classes

   Any

3. final def ##(): Int

   Definition Classes

   AnyRef → Any

4. final def ==(arg0: AnyRef): Boolean

   Definition Classes

   AnyRef

5. final def ==(arg0: Any): Boolean

   Definition Classes

   Any

6. final def asInstanceOf[T0]: T0

   Definition Classes

   Any

7. def clearHistory(state: Table): Table

   Clear the history information in the state

   Clear the history information in the state

   state

   returns

   Definition Classes

   Adam → OptimMethod

8. def clone(): AnyRef

   Attributes

   protected[java.lang]

   Definition Classes

   AnyRef

   Annotations

   @throws( ... )

9. final def eq(arg0: AnyRef): Boolean

   Definition Classes

   AnyRef

10. def equals(arg0: Any): Boolean

    Definition Classes

    AnyRef → Any

11. def finalize(): Unit

    Attributes

    protected[java.lang]

    Definition Classes

    AnyRef

    Annotations

    @throws( classOf[java.lang.Throwable] )

12. final def getClass(): Class[_]

    Definition Classes

    AnyRef → Any

13. def getHyperParameter(config: Table): String

    Get hyper parameter from config table.

    Get hyper parameter from config table.

    config

    a table contains the hyper parameter.

    Definition Classes

    OptimMethod

14. def hashCode(): Int

    Definition Classes

    AnyRef → Any

15. final def isInstanceOf[T0]: Boolean

    Definition Classes

    Any

16. final def ne(arg0: AnyRef): Boolean

    Definition Classes

    AnyRef

17. final def notify(): Unit

    Definition Classes

    AnyRef

18. final def notifyAll(): Unit

    Definition Classes

    AnyRef

19. def optimize(feval: (Tensor[T]) ⇒ (T, Tensor[T]), parameter: Tensor[T], config: Table, state: Table): (Tensor[T], Array[T])

    An implementation of Adam http://arxiv.

    An implementation of Adam http://arxiv.org/pdf/1412.6980.pdf

    feval

    a function that takes a single input (X), the point of a evaluation, and returns f(X) and df/dX

    parameter

    the initial point

    config

    a table with hyper-parameters for the optimizer config("learningRate") : learning rate config("learningRateDecay") : learning rate decay config("beta1") : first moment coefficient config("beta2") : second moment coefficient config("Epsilon"): for numerical stability

    state

    a table describing the state of the optimizer; after each call the state is modified state("s") : 1st moment variables state("r"): 2nd moment variables state("denom"): A tmp tensor to hold the sqrt(v) + epsilon

    returns

    the new x vector and the function list {fx}, evaluated before the update

    Definition Classes

    Adam → OptimMethod

20. final def synchronized[T0](arg0: ⇒ T0): T0

    Definition Classes

    AnyRef

21. def toString(): String

    Definition Classes

    AnyRef → Any

22. def updateHyperParameter(config: Table, state: Table): Unit

    Update hyper parameter.

    Update hyper parameter. We have updated hyper parameter in method optimize(). But in DistriOptimizer, the method optimize() is only called on the executor side, the driver's hyper parameter is unchanged. So this method is using to update hyper parameter on the driver side.

    config

    config table.

    state

    state Table.

    returns

    A string.

    Definition Classes

    OptimMethod

23. final def wait(): Unit

    Definition Classes

    AnyRef

    Annotations

    @throws( ... )

24. final def wait(arg0: Long, arg1: Int): Unit

    Definition Classes

    AnyRef

    Annotations

    @throws( ... )

25. final def wait(arg0: Long): Unit

    Definition Classes

    AnyRef

    Annotations

    @throws( ... )